To the list of courses || RASA2018 || To the theme || Estonian

Exercise 3967. Points 2, theme: Spatial Autocorrelation

Open exercise
The attached file contains precipitation in May measured in the Baltic weather observation stations in different years.
  1. Which p< 0.01 level spatio-temporal patterns are evident in these data?
  2. Add the 3D autocorrelogram.
  3. Would you use this autocorrelogram when predicting precipitation amount for May 2028 in Tallinn knowing only the corresponding value for Tartu in 2017? If yes, then explain how.
Data: 3D_autocorr_example_full_dataset.zip

Instructions

The input data for the SDC autocorrelation can be spatially one, two or three dimensional.
  • Select 3D, Discrete distance zones and Third dimension separately.
  • Copy the attached data to the input.
  • The parameters are not specified in this exercise. In general, one should try different settings as the scale of 3D patterns is not known. The mentor used time interval 1 year and spatial interval 20 km.
  • Remember that lag used when calculating omnidirectional autocorrelation has no direction.
  • The coordinates are in meters, use kilometers when explaining the results.
Log in to send your results and to see the expected answer and responses from other students.